Artificial Intelligence Engineer

About the Role

At Independence OS, we're building AI-native infrastructure to fundamentally transform how healthcare operates. We're reimagining healthcare workflows from first principles, designing systems where AI agents can autonomously execute complex operational and clinical-administrative tasks. We're looking for an Artificial Intelligence Engineer who can architect, build, deploy, and scale production-grade AI systems powering the next generation of US primary care. You'll work across medical documentation, AI-powered patient communication, revenue cycle management, provider credentialing, value-based care, and compliance workflows. This is a hands-on engineering role with end-to-end ownership, from system architecture and experimentation to production deployment and continuous improvement.

Key Responsibilities

• Architect AI-native systems: Design scalable architectures built around LLMs, AI agents, and intelligent orchestration rather than traditional rule-based workflows.
• Build agentic AI systems: Develop autonomous and multi-agent workflows capable of reasoning, using tools, maintaining context, and executing complex healthcare operations.
• Develop production-grade AI applications: Build and deploy AI-powered solutions across medical scribes, conversational voice agents, billing, credentialing, and other healthcare workflows.
• Own the complete AI lifecycle: Take responsibility for system design, prototyping, experimentation, deployment, monitoring, and optimization.
• Optimize AI performance: Improve model and agent accuracy, latency, reliability, safety, and inference costs through systematic evaluations and experimentation.
• Build robust AI infrastructure: Implement retrieval systems, context management, tool integrations, structured outputs, observability, and failure recovery mechanisms.
• Solve real healthcare problems: Collaborate directly with product managers, software engineers, and clinical stakeholders to translate complex healthcare challenges into scalable AI solutions.
• Engineer for real-world deployment: Build secure, reliable systems that operate within healthcare privacy, security, and regulatory requirements, including HIPAA.

Requirements & Tech Stack

• Strong proficiency in Python and experience building production-grade software systems.
• Hands-on experience developing applications using LLMs and modern generative AI technologies.
• Understanding of agentic AI architectures, orchestration frameworks, tool calling, and multi-step workflows.
• Experience working with model APIs, retrieval-augmented generation (RAG), embeddings, vector databases, and context management.
• Strong understanding of backend engineering, APIs, asynchronous processing, distributed systems, and cloud infrastructure.
• Ability to evaluate and optimize AI systems for accuracy, latency, reliability, and cost.
• Strong problem-solving skills and the ability to independently architect and own complex technical solutions.
• A product-oriented engineering mindset, with a willingness to take ownership beyond model development.

Good to Have

• Experience building real-time conversational or voice AI systems.
• Familiarity with healthcare workflows, EHR integrations, FHIR/HL7, or US healthcare operations.
• Experience with LLM evaluation frameworks, fine-tuning, and model optimization.
• Experience deploying AI systems in regulated or high-reliability environments.

Why Independence OS?

You'll work on AI systems designed to operate in real healthcare environments. You'll have the opportunity to build AI-native products from the ground up, solve complex problems across US primary care, collaborate closely with a multidisciplinary team, and own meaningful systems from conception to production. We're looking for engineers who don't just use AI models, but understand how to engineer complete systems around them.